© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56776
    Prev
    Next
    INDEX
    Explanations

    field of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æį¢å±Ĭ
    -0.09
    æŁıæŀĹ
    -0.09
    omics
    -0.09
    æľ¬è½®
    -0.08
    çĵľ
    -0.08
    ä¼łå¯¼
    -0.08
    çĵ£
    -0.08
     chÃŃ
    -0.08
    iena
    -0.08
    é¹ı
    -0.08
    POSITIVE LOGITS
    人士
    0.12
    å·¥ä½ľèĢħ
    0.10
    work
    0.10
    walker
    0.09
    LER
    0.09
    åĨħçļĦ
    0.09
    éļĺ
    0.09
     зÑĢениÑı
    0.09
    è´»
    0.09
    mates
    0.09
    Activations Density 0.074%

    No Known Activations